© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34292
    Prev
    Next
    INDEX
    Explanations

    buoyancy and floating objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iker
    -0.09
    ç²īç¢İ
    -0.09
    严
    -0.09
    odule
    -0.08
    bro
    -0.08
    Õº
    -0.08
    ÙĨد
    -0.08
    รว
    -0.08
    mons
    -0.08
    ожно
    -0.08
    POSITIVE LOGITS
    ancy
    0.11
    ance
    0.10
    ä¸ĢæŶ
    0.10
    æ³Ĭ
    0.09
    ramid
    0.09
    une
    0.09
     bá»ģ
    0.09
    berman
    0.09
    ILI
    0.09
    ctl
    0.09
    Activations Density 0.008%

    No Known Activations